A Wavelet-based Dual-stream Network for Underwater Image Enhancement

TL;DR

This paper introduces a wavelet-based dual-stream neural network that effectively enhances underwater images by separately addressing color correction and detail enhancement, leading to improved visual quality with low computational cost.

Contribution

The proposed method uniquely combines wavelet decomposition with dual-stream networks for simultaneous color correction and detail enhancement in underwater images.

Findings

Effective color correction demonstrated on real and synthetic datasets.

Significant blur removal with preserved image details.

Low computational complexity compared to existing methods.

Abstract

We present a wavelet-based dual-stream network that addresses color cast and blurry details in underwater images. We handle these artifacts separately by decomposing an input image into multiple frequency bands using discrete wavelet transform, which generates the downsampled structure image and detail images. These sub-band images are used as input to our dual-stream network that incorporates two sub-networks: the multi-color space fusion network and the detail enhancement network. The multi-color space fusion network takes the decomposed structure image as input and estimates the color corrected output by employing the feature representations from diverse color spaces of the input. The detail enhancement network addresses the blurriness of the original underwater image by improving the image details from high-frequency sub-bands. We validate the proposed method on both real-world and synthetic underwater datasets and show the effectiveness of our model in color correction and blur removal with low computational complexity.